ALY6040-80514 Group 3

Group Members: - Karolina Grodzinska, Mirav Parekh, Rhythm Desai, Vaidehi Chauhan

We have imported pandas ,numpy for basic data analysis. Seaborn and matplotlib for data visualization. Folium for maps.

Data Exploration , Visualization and Processing

We can drop the columns with less categories.Checking whether boolean and categorical features contain sufficient numbers of instances in each category to make them worth including.It can be seen that several columns only contain one category and can be dropped while preprocessing.

Data Preprocessing

Data Visualization

Multi-Collinearity

Decision Tree

Feature Importance

Cross Validation

Random Forest Regressor

Feature Importance

Hyperparameter Tuning

Cross Validation

XGBoost

Feature Importance

Hyperparameter Tuning

Cross Validation

Linear Regression

Cross Validation

Feature Importance

Regularization